Caliber Flex 1B by OnePass. Decision-only model, exactly 1,000,000,000 parameters.
Contrastive Language Models score a state against a set of candidate actions with a contrastive objective. Two projection heads on frozen Qwen3-8B embeddings, trained with InfoNCE; clm-serve maps Choice, Score and Noul onto candidate ranking.
Decides
choice, noul, score
choice, score, noul, rank, classify, route
Architecture
llm
clm
Fine-tuned from
qwen/qwen3.5-0.8b-base
qwen/qwen3-8b
License
caliber-flex-non-commercial-1.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
—
—
Calibration error
—
—
Valid action rate
—
—
Median latency
—
—
p95 latency
—
—
Evaluation suite
Figures are from each model’s manifest; accuracy and latency are what the publishers report, on their own suites and hardware. Add a third model.
Questions
What is the difference between caliber-flex-1b and clm?
caliber-flex-1b is from onepass and clm from Contrastive-LM. Both have open weights you can download and run. Both answer choice, noul and score questions. Only clm answers rank, classify and route. caliber-flex-1b is licensed other; clm, apache-2.0.
Which is more accurate, caliber-flex-1b or clm?
Neither publishes an accuracy figure. Test both on your own labelled examples.
Which is cheaper, caliber-flex-1b or clm?
caliber-flex-1b: Free (open weights). clm: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run caliber-flex-1b or clm locally?
Yes, both: systemone pull onepass/caliber-flex-1b and systemone pull contrastive-lm/clm download the weights.
